Model comparison
GPT-3.5-turbo vs Phi-1.5
GPT-3.5-turbo has enough public results to be ranked (#345); Phi-1.5 does not yet, so treat this comparison as directional.
Last verified . 6 shared benchmarks.
MicrosoftSummary
- They share 6 benchmarks with published results for both.
- Phi-1.5 has downloadable open weights; the other is API-only.
Side by side
| GPT-3.5-turbo | Phi-1.5 | |
|---|---|---|
| Provider | OpenAI | Microsoft |
| Noometry Index | 23.1 | — |
| Released | 2023-03-01 | 2023-09-11 |
| Weights | Proprietary | Open |
| Context window | 16K | — |
| Max output | 4K | — |
| Input $ / M tokens | $0.50 | — |
| Output $ / M tokens | $1.50 | — |
| Results tracked | 44 | 7 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
GPT-3.5-turbo: 23.5 (#326), Phi-1.5: —
| Benchmark | GPT-3.5-turbo | Phi-1.5 |
|---|---|---|
| WeirdML | 3.5% | — |
| BigCodeBench Instruct | 39.1% | — |
| LMArena Coding | 1137 | — |
| BigCodeBench Complete | 50.6% | — |
| HumanEval+ | 70.7% | — |
| MBPP+ | 69.7% | — |
Agentic & Tool Use Not comparable
GPT-3.5-turbo: —, Phi-1.5: —
| Benchmark | GPT-3.5-turbo | Phi-1.5 |
|---|---|---|
| METR Time Horizons | 21.5% | — |
Reasoning Not comparable
GPT-3.5-turbo: 13.3 (#328), Phi-1.5: —
| Benchmark | GPT-3.5-turbo | Phi-1.5 |
|---|---|---|
| Epoch Capabilities Index | 118.48 | 90.82 |
| WinoGrande | 81.6% | 73.4% |
| Chess Puzzles | 0% | — |
| LMArena Hard Prompts | 1108 | — |
| Mystery Game Puzzles | 3% | — |
| DTBench | 48.5% | — |
| LMCA | 9.7% | — |
| Adversarial NLI | 58.1% | — |
| BIG-Bench Hard | 61.6% | — |
| CommonsenseQA 2.0 | 57% | — |
| ForecastBench | 50.4 | — |
| HellaSwag | — | 47.6% |
Math Not comparable
GPT-3.5-turbo: 6.0 (#321), Phi-1.5: —
| Benchmark | GPT-3.5-turbo | Phi-1.5 |
|---|---|---|
| FrontierMath (Tiers 1-3) | 0% | — |
| OTIS Mock AIME 2024-2025 | 2.2% | — |
| LMArena Math | 1142 | — |
| MATH Level 5 | 15.9% | — |
| GSM8K | 57.8% | — |
Knowledge Not comparable
GPT-3.5-turbo: 10.0 (#298), Phi-1.5: —
| Benchmark | GPT-3.5-turbo | Phi-1.5 |
|---|---|---|
| ARC (AI2) Challenge | 87.4% | 44.4% |
| BoolQ | 87% | 75.8% |
| MMLU | 71.4% | 37.6% |
| OpenBookQA | 86% | 37.2% |
| GPQA Diamond | 28% | — |
| LMArena Expert | 1070 | — |
| TriviaQA | 85.8% | — |
Multilingual Not comparable
GPT-3.5-turbo: 31.6 (#253), Phi-1.5: —
| Benchmark | GPT-3.5-turbo | Phi-1.5 |
|---|---|---|
| LMArena Non-English | 1108 | — |
| LMArena Chinese | 1075 | — |
| LMArena French | 1117 | — |
| LMArena German | 1090 | — |
| LMArena Japanese | 1043 | — |
| LMArena Korean | 1019 | — |
| LMArena Russian | 1123 | — |
| LMArena Spanish | 1120 | — |
Instruction Following Not comparable
GPT-3.5-turbo: 58.1 (#257), Phi-1.5: —
| Benchmark | GPT-3.5-turbo | Phi-1.5 |
|---|---|---|
| LMArena Instruction Following | 1119 | — |
Long Context Not comparable
GPT-3.5-turbo: 34.0 (#249), Phi-1.5: —
| Benchmark | GPT-3.5-turbo | Phi-1.5 |
|---|---|---|
| LMArena Longer Query | 1121 | — |
Writing & Preference Not comparable
GPT-3.5-turbo: 25.4 (#300), Phi-1.5: —
| Benchmark | GPT-3.5-turbo | Phi-1.5 |
|---|---|---|
| LMArena Text | 1125 | — |
| LMArena Creative Writing | 1092 | — |
| EQ-Bench Creative Writing | 451 | — |
| LMArena Multi-Turn | 1117 | — |
Frequently asked questions
Is GPT-3.5-turbo better than Phi-1.5?
GPT-3.5-turbo has enough public results to be ranked (#345); Phi-1.5 does not yet, so treat this comparison as directional.
How many benchmarks do GPT-3.5-turbo and Phi-1.5 share?
6 benchmarks have published results for both models. GPT-3.5-turbo has 44 scored results on Noometry and Phi-1.5 has 7.